Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    isiin
    0.45
    aita
    0.44
    боро
    0.43
    ivist
    0.40
    を送
    0.40
    اما
    0.39
    aba
    0.39
    よりも
    0.39
     چاہتا
    0.39
    treasure
    0.39
    POSITIVE LOGITS
     espèce
    0.44
     ensues
    0.41
    ড্ডা
    0.41
     países
    0.40
     emas
    0.40
     Sinn
    0.40
     konkrét
    0.40
     dreary
    0.39
     aquí
    0.39
     posición
    0.39
    Act Density 0.003%

    No Known Activations